VQV Signal

AI AT WORK WATCH TECHNICAL

Rounds shows Claude Code session outputs on one canvas, with notes linked back to chats

According to a post on X by @rahulbhadoriiya, they tried Rounds, a tool by @krispuckett that reads Claude Code chats. It lays out the screens, published pages and changed files those sessions produced on one canvas, sorted by project and day. The canvas cannot be edited: users pin a note to a screen, and that note goes back to the chat that made it. The maker describes Rounds as local, private and free, installed with npx.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-21T14:55:00+00:00 Detected 2026-11-21T20:01:30+00:00
View original source

According to a post on X by @rahulbhadoriiya, they tried Rounds, a tool by @krispuckett that reads Claude Code chats. It lays out the screens, published pages and changed files those sessions produced on one canvas, sorted by project and day. The canvas cannot be edited: users pin a note to a screen, and that note goes back to the chat that made it. The maker describes Rounds as local, private and free, installed with npx.

AI-assisted summary based on the listed source.

@rahulbhadoriiya tried Rounds by @krispuckett, which reads Claude Code chats and lays out the screens, published pages and changed files they produced on one canvas, sorted by project and day. You can't edit anything on it; you pin a note on a screen and that note goes back to the chat that made it. The maker...

Developers who use Claude Code across many sessions could get one view of what those sessions produced. Because pinned notes link back to the originating chat, feedback can be tied directly to the work that prompted it. The local, private and free claims come from the maker as reported in the post, and VQV has not independently checked them.

Teams using AI at work may want to compare this against current productivity and review workflows.

Signal Strength 79% Technical label WATCH Public Interest 49 Category AI AT WORK Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 73 Practical Impact Score 28 Novelty Interest Score 70 Consequence Score 22 Curiosity Score 16 Shareability Score 62

VQV surfaced this signal because it is recent, relevant to AI Coding Tools, connected to Scobleizer News Pulse (X).